Instructions to use UniverseTBD/astrollama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UniverseTBD/astrollama with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="UniverseTBD/astrollama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UniverseTBD/astrollama")
model = AutoModelForCausalLM.from_pretrained("UniverseTBD/astrollama", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use UniverseTBD/astrollama with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UniverseTBD/astrollama"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UniverseTBD/astrollama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UniverseTBD/astrollama

SGLang

How to use UniverseTBD/astrollama with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "UniverseTBD/astrollama" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UniverseTBD/astrollama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "UniverseTBD/astrollama" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UniverseTBD/astrollama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use UniverseTBD/astrollama with Docker Model Runner:
```
docker model run hf.co/UniverseTBD/astrollama
```

joshnguyen commited on Sep 16, 2023

Commit

45a37da

1 Parent(s): d41ff0e

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -85,5 +85,5 @@ inputs.to(model.device)
 outputs = model(**inputs, output_hidden_states=True)
 # Last layer of the hidden states. Get average embedding of all tokens
-embeddings = outputs["hidden_states"][-1][:, :, ...].mean().detach().cpu().numpy()
 ```

 outputs = model(**inputs, output_hidden_states=True)
 # Last layer of the hidden states. Get average embedding of all tokens
+embeddings = outputs["hidden_states"][-1][:, 1:, ...].mean(1).detach().cpu().numpy()
 ```